Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    introducing lists or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ></
    0.17
    сить
    0.17
     détermination
    0.17
     *)
    0.17
    чины
    0.17
    <unused2173>
    0.16
     parametrization
    0.16
     WOULD
    0.16
    ="
    0.16
    ても
    0.16
    POSITIVE LOGITS
     including
    0.39
     featuring
    0.39
     covering
    0.39
     focusing
    0.39
     offering
    0.38
     allowing
    0.37
     consisting
    0.36
     encompassing
    0.36
     representing
    0.36
     culminating
    0.36
    Act Density 0.977%

    No Known Activations